hustvl / VAD

[ICCV 2023] VAD: Vectorized Scene Representation for Efficient Autonomous Driving

Home Page:https://arxiv.org/abs/2303.12077

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

About pretrained weights

xiaoke0621 opened this issue · comments

Hello!
Are the pretrained weights of vad and vad-tiny the following one? Are both used the same?

img_norm_cfg = dict( mean=[103.530, 116.280, 123.675], std=[1.0, 1.0, 1.0], to_rgb=False)